anti-cherry-pick

Official

Enforce complete transparent reporting.

AuthorEvoClaw
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Phase 4 reporting discipline activation ensures every seed, result, and failure is recorded and reported to prevent selective outcomes from skewing conclusions.

Core Features & Use Cases

  • Mandatory reporting of all seeds, all results, and all failures with aggregated statistics (mean ± std or 95% CI) to avoid cherry-picking.
  • Negative results are data and must be stored in docs/05_execution/negative-results.md; nothing is silently dropped or deleted.
  • Fair baselines require equal compute budgets, data, preprocessing pipelines, and hyperparameter search budgets across methods.
  • Equivalent access ensures all methods share the same pretrained models, data, and external resources.
  • Gate-based discipline enforces full transparency across all datasets listed in the evaluation protocol.

Quick Start

Activate the Phase 4 reporting gates and begin recording all seeds, results, and failures immediately.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: anti-cherry-pick
Download link: https://github.com/EvoClaw/amplify/archive/main.zip#anti-cherry-pick

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.